Brain Machine Interface Velocity Vector Modification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current brain-machine interfaces (BMIs) operate slower and less accurately than native arm movements, and they do not sustain performance across hours and days without human intervention, limiting their effectiveness in controlling prosthetic devices.
Innovation Solution
A brain machine interface is developed that maps neural signals to intention estimating kinematics, using a modified Kalman filter to model velocities as intentions and positions as feedback, allowing for more accurate and sustained control of prosthetic devices by refining velocity vectors and incorporating position feedback to reduce position-dependent neural data stream instability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If current BMI control algorithms are used, then prosthetic devices can be controlled, but the control speed and accuracy are considerably slower and less accurate than native arm movements
Solution Approach 1:
The patent modifies the control algorithm by changing the parameter being decoded from velocity to acceleration. This parameter transformation allows the system to achieve both high speed and high accuracy by capturing the intent behind movements more directly, rather than merely tracking velocity, thereby resolving the contradiction between control speed and control accuracy.
Solution Approach 2:
The patent replaces traditional velocity-based control mechanisms with an acceleration-based decoding system. By substituting the mechanical control paradigm (velocity control) with a neural-inspired paradigm (acceleration control that mirrors biological motor commands), the system achieves native-like control performance in both speed and accuracy.
2Reliability
If current BMI systems operate without human intervention, then automated control is achieved, but performance does not sustain across hours and days
Solution Approach 1:
The patent implements a self-adjusting control algorithm that automatically adapts to neural signal variations over time without requiring human re-calibration. The system monitors its own performance and dynamically adjusts decoding parameters, enabling sustained reliable operation across hours and days while maintaining full automation.
Solution Approach 2:
The patent introduces dynamic adaptation into the BMI system, where the control algorithm continuously evolves its parameters based on incoming neural data statistics. This dynamic behavior allows the system to maintain optimal performance despite drift in neural signals, achieving long-term reliability without human intervention.
3Measurement precision
If velocity vectors are modified at discrete intervals, then intention estimation is improved, but computational processing time increases
Solution Approach 1:
The patent pre-computes and stores acceleration-to-velocity transformation matrices during a calibration phase, so that during real-time operation, only simple matrix multiplications are needed. This preliminary preparation reduces online computational burden while maintaining high intention estimation accuracy through the use of pre-optimized transformation parameters.
Data Source
AI summary
Artificial control of a prosthetic device is provided. A brain machine interface contains a mapping of neural signals and corresponding intention estimating kinematics (e.g. positions and velocities) of a limb trajectory. The prosthetic device is controlled by the brain machine interface. During the control of the prosthetic device, a modified brain machine interface is developed by modifying the vectors of the velocities defined in the brain machine interface. The modified brain machine interface includes a new mapping of the neural signals and the intention estimating kinematics that can now be used to control the prosthetic device using recorded neural brain signals from a user of the prosthetic device. In one example, the intention estimating kinematics of the original and modified brain machine interface includes a Kalman filter modeling velocities as intentions and positions as feedback.